===================================================================
@@ -3959,6 +3959,15 @@
"shufflebytes\t%0, %r2, %r3"
[(set_attr "type" "X0")])
+(define_insn "insn_shufflebytes1"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (unspec:DI [(match_operand:DI 1 "reg_or_0_operand" "rO")
+ (match_operand:DI 2 "reg_or_0_operand" "rO")]
+ UNSPEC_INSN_SHUFFLEBYTES))]
+ ""
+ "shufflebytes\t%0, %r1, %r2"
+ [(set_attr "type" "X0")])
+
;; stores
(define_expand "insn_st"
===================================================================
@@ -193,6 +193,7 @@ enum tilegx_builtin
TILEGX_INSN_SHRU,
TILEGX_INSN_SHRUX,
TILEGX_INSN_SHUFFLEBYTES,
+ TILEGX_INSN_SHUFFLEBYTES1,
TILEGX_INSN_ST,
TILEGX_INSN_ST1,
TILEGX_INSN_ST2,
===================================================================
@@ -2897,6 +2897,7 @@ static struct tile_builtin_info tilegx_b
{ CODE_FOR_lshrdi3, NULL }, /* shru */
{ CODE_FOR_lshrsi3, NULL }, /* shrux */
{ CODE_FOR_insn_shufflebytes, NULL }, /* shufflebytes */
+ { CODE_FOR_insn_shufflebytes1, NULL }, /* shufflebytes1 */
{ CODE_FOR_insn_st, NULL }, /* st */
{ CODE_FOR_insn_st1, NULL }, /* st1 */
{ CODE_FOR_insn_st2, NULL }, /* st2 */
@@ -3225,6 +3226,7 @@ static const struct tilegx_builtin_def t
{ "__insn_shrux", TILEGX_INSN_SHRUX, true, "iii" },
{ "__insn_shruxi", TILEGX_INSN_SHRUX, true, "iii" },
{ "__insn_shufflebytes", TILEGX_INSN_SHUFFLEBYTES, true, "llll" },
+ { "__insn_shufflebytes1", TILEGX_INSN_SHUFFLEBYTES1, true, "lll" },
{ "__insn_st", TILEGX_INSN_ST, false, "vpl" },
{ "__insn_st1", TILEGX_INSN_ST1, false, "vpl" },
{ "__insn_st2", TILEGX_INSN_ST2, false, "vpl" },
This patch adds the __insn_shufflebytes1, which takes only one argument. result = __insn_shufflebytes1(input, select); is equivalent to: result = __insn_shufflebytes(result, input, select); It has the advantage that the compiler will not waste a cycle initializing result unnecessarily. It is the user's responsibility to ensure that the select value is only selecting bytes from the second operand. This has been backported to 4.7 and 4.8. * config/tilegx/tilegx-builtins.h (enum tilegx_builtin): Add TILEGX_INSN_SHUFFLEBYTES1. * config/tilegx/tilegx.c (tilegx_builtin_info): Add entry for shufflebytes1. (tilegx_builtins): Ditto. * config/tilegx/tilegx.md (insn_shufflebytes1): New pattern.